© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68820
    Prev
    Next
    INDEX
    Explanations

    Evaluation and state

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “performance,” effectively spotting mentions of performance evaluation or metrics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bedding
    -0.07
    IGHLIGHT
    -0.06
     gerçekten
    -0.06
     nord
    -0.06
    _sym
    -0.06
     martyr
    -0.06
    liest
    -0.06
    	object
    -0.06
    Cas
    -0.06
     دس
    -0.06
    POSITIVE LOGITS
     droit
    0.07
    ulen
    0.07
    Weapons
    0.07
    (cond
    0.07
    配置
    0.06
    }*
    0.06
    _INFO
    0.06
     조회
    0.06
    .providers
    0.06
    反
    0.06
    Activations Density 0.049%

    No Known Activations